Merge pull request #48 from cthoyt/add-bioregistry-prefixes

Add prefix synonyms from the Bioregistry

src/prefixmaps/data/prefixcc.csv

@@ -711,6 +711,7 @@ prefixcc,environ,http://eulersharp.sourceforge.net/2003/03swap/environment#,cano
 prefixcc,eol,http://purl.org/biodiversity/eol/,canonical
 prefixcc,ep,http://eprints.org/ontology/,namespace_alias
 prefixcc,epcis,https://ns.gs1.org/epcis/,canonical
+prefixcc,epo,http://data.europa.eu/a4g/ontology#,canonical
 prefixcc,eppl,https://w3id.org/ep-plan#,canonical
 prefixcc,epplan,https://w3id.org/ep-plan#,namespace_alias
 prefixcc,eppo,https://gd.eppo.int/taxon/,canonical
@@ -929,7 +930,7 @@ prefixcc,gfo,http://www.onto-med.de/ontologies/gfo.owl#,canonical
 prefixcc,gg,http://www.gemeentegeschiedenis.nl/gg-schema#,canonical
 prefixcc,ggbn,http://data.ggbn.org/schemas/ggbn/terms/,canonical
 prefixcc,ghga,http://w3id.org/ghga/,canonical
-prefixcc,gist,http://ontologies.semanticarts.com/gist#,canonical
+prefixcc,gist,http://ontologies.semanticarts.com/gist/,canonical
 prefixcc,giving,http://ontologi.es/giving#,canonical
 prefixcc,gl,http://schema.geolink.org/,canonical
 prefixcc,gldp,http://www.w3.org/ns/people#,canonical
@@ -1209,7 +1210,7 @@ prefixcc,lda,http://purl.org/linked-data/api/vocab#,namespace_alias
 prefixcc,ldap,http://purl.org/net/ldap/,canonical
 prefixcc,ldc,https://tac.nist.gov/tracks/SM-KBP/2018/ontologies/SeedlingOntology#,canonical
 prefixcc,lden,http://www.linklion.org/lden/,canonical
-prefixcc,ldes,http://w3id.org/ldes#,canonical
+prefixcc,ldes,https://w3id.org/ldes#,canonical
 prefixcc,ldl,https://w3id.org/ldpdl/ns#,canonical
 prefixcc,ldn,https://www.w3.org/TR/ldn/#,canonical
 prefixcc,ldp,http://www.w3.org/ns/ldp#,canonical

src/prefixmaps/data/w3id.csv

@@ -292,6 +292,7 @@ w3id,drone,https://w3id.org/drone/,canonical
 w3id,dsa,https://w3id.org/dsa/,canonical
 w3id,dsd,https://w3id.org/dsd/,canonical
 w3id,dso,https://w3id.org/dso/,canonical
+w3id,dspace,https://w3id.org/dspace/,canonical
 w3id,dstv,https://w3id.org/dstv/,canonical
 w3id,dsv-ontology,https://w3id.org/dsv-ontology/,canonical
 w3id,dts,https://w3id.org/dts/,canonical
@@ -351,6 +352,7 @@ w3id,euro-nmd-kpis,https://w3id.org/euro-nmd-kpis/,canonical
 w3id,EUTaxO,https://w3id.org/EUTaxO/,canonical
 w3id,evdoxus,https://w3id.org/evdoxus/,canonical
 w3id,EVENTSKG-Dataset,https://w3id.org/EVENTSKG-Dataset/,canonical
+w3id,everycred,https://w3id.org/everycred/,canonical
 w3id,EVI,https://w3id.org/EVI/,canonical
 w3id,EXACT,https://w3id.org/EXACT/,canonical
 w3id,examode,https://w3id.org/examode/,canonical
@@ -402,6 +404,7 @@ w3id,fog,https://w3id.org/fog/,canonical
 w3id,food,https://w3id.org/food/,canonical
 w3id,foodallergen,https://w3id.org/foodallergen/,canonical
 w3id,foodie,https://w3id.org/foodie/,canonical
+w3id,foodpairing_inspire_kg,https://w3id.org/foodpairing_inspire_kg/,canonical
 w3id,foops,https://w3id.org/foops/,canonical
 w3id,forecasting4eepsa,https://w3id.org/forecasting4eepsa/,canonical
 w3id,fox,https://w3id.org/fox/,canonical
@@ -619,6 +622,7 @@ w3id,media,https://w3id.org/media/,canonical
 w3id,mediatype,https://w3id.org/mediatype/,canonical
 w3id,medred,https://w3id.org/medred/,canonical
 w3id,medtag,https://w3id.org/medtag/,canonical
+w3id,meta,https://w3id.org/meta/,canonical
 w3id,meta-share,https://w3id.org/meta-share/,canonical
 w3id,metadocencia,https://w3id.org/metadocencia/,canonical
 w3id,metamodeling,https://w3id.org/metamodeling/,canonical
@@ -700,7 +704,6 @@ w3id,oac,https://w3id.org/oac/,canonical
 w3id,oak,https://w3id.org/oak/,canonical
 w3id,obda,https://w3id.org/obda/,canonical
 w3id,obelisk,https://w3id.org/obelisk/,canonical
-w3id,obio,https://w3id.org/obio/,canonical
 w3id,obo,https://w3id.org/obo/,canonical
 w3id,obpa,https://w3id.org/obpa/,canonical
 w3id,obpd,https://w3id.org/obpd/,canonical
@@ -716,6 +719,7 @@ w3id,oebDatasets,https://w3id.org/oebDatasets/,canonical
 w3id,oerbase,https://w3id.org/oerbase/,canonical
 w3id,ofo,https://w3id.org/ofo/,canonical
 w3id,oho,https://w3id.org/oho/,canonical
+w3id,okg,https://w3id.org/okg/,canonical
 w3id,okn,https://w3id.org/okn/,canonical
 w3id,olu,https://w3id.org/olu/,canonical
 w3id,omg,https://w3id.org/omg/,canonical

src/prefixmaps/ingest/ingest_bioregistry.py

@@ -9,6 +9,9 @@
 # Problematic records, look into later
 SKIP = {"gro"}
 
+#: Problematic synonym records cause the issue in https://github.com/linkml/prefixmaps/issues/50
+PROBLEMATIC_CURIE_PREFIX_SYNONYMS_RECORDS = {"wikidata"}
+
 
 def from_bioregistry_upper(**kwargs) -> Context:
     """
@@ -76,5 +79,10 @@ def from_bioregistry(upper=False, canonical_idorg=True, filter_dubious=True) ->
             continue
         preferred = record.prefix == bioregistry.get_preferred_prefix(record.prefix)
         context.add_prefix(record.prefix, record.uri_prefix, preferred=preferred)
-        # TODO add synonyms, do in later PR since it will increase diff and complexity of review
+        if record.prefix not in PROBLEMATIC_CURIE_PREFIX_SYNONYMS_RECORDS:
+            for s in record.prefix_synonyms:
+                context.add_prefix(s, record.uri_prefix, preferred=preferred)
+        # TODO future, add URI prefix synonyms
+        # for s in record.uri_prefix_synonyms:
+        #     context.add_prefix(record.prefix, s, status=StatusType.namespace_alias, preferred=preferred)
     return context

tests/test_core/test_prefixmaps.py

@@ -3,6 +3,7 @@
 """
 import unittest
 
+import prefixmaps
 from prefixmaps.datamodel.context import StatusType
 from prefixmaps.io.parser import context_from_file, load_context, load_multi_context
 from prefixmaps.io.writer import context_to_file
@@ -183,3 +184,12 @@ def test_from_upstream(self):
     # def test_meta(self):
     #     ctxts = load_contexts_meta()
     # print(ctxts)
+
+    def test_synonyms(self):
+        canonical = "PUBMED:1234"
+        converter = prefixmaps.load_converter("merged")
+        # TODO "pmid:1234", "pubmed:1234"
+        others = ["PMID:1234", "MEDLINE:1234", canonical]
+        for curie in others:
+            with self.subTest(curie=curie):
+                self.assertEqual(canonical, converter.standardize_curie(curie))